Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48953
    Prev
    Next
    INDEX
    Explanations

    Math expressions/proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _REPLY
    -0.09
    Reply
    -0.08
    .reply
    -0.08
    (reply
    -0.08
     bookmarks
    -0.08
     Reply
    -0.08
    	reply
    -0.08
    Consent
    -0.08
     replies
    -0.08
     replying
    -0.08
    POSITIVE LOGITS
     positivity
    0.09
     positive
    0.08
    证明
    0.08
     divisor
    0.08
     अथ
    0.08
     अभ
    0.08
     geprü
    0.08
    +y
    0.08
     zeigen
    0.08
     positiven
    0.08
    Activations Density 0.044%

    No Known Activations